cs.CL（2026-06-17）

📊 共 19 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (14 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (14 篇)

#题目一句话要点标签🔗⭐
1 As Easy as Rocket Science: Assessing the Ability of Large Language Models to Interpret Negation in Figurative Language 提出新注释以评估大型语言模型对否定与比喻语言的理解能力 large language model
2 Enhancing Decision-Making with Large Language Models through Multi-Agent Fictitious Play 提出多代理虚拟博弈以解决决策复杂性问题 large language model
3 Dango: A Strictly L1-Only Large Language Model for Studying Second Language Acquisition 提出Dango模型以研究第二语言习得中的L1到L2转移问题 large language model
4 IndicContextEval: A Benchmark for Evaluating Context Utilisation in Audio Large Language Models Across 8 Indic Languages 提出IndicContextEval以评估音频大语言模型的上下文利用能力 large language model
5 Learning Robust Pair Confidence for Multimodal Emotion-Cause Pair Extraction 提出RPCL以解决多模态情感-原因对提取中的信心脆弱问题 multimodal
6 Output Vector Editing for Memorization Mitigation in Large Language Models 提出输出向量编辑以缓解大语言模型的记忆问题 large language model
7 TW-LegalBench: Measuring Taiwanese Legal Understanding 提出TW-LegalBench以评估台湾法律理解能力 large language model
8 PEC-Home: Interpretation of Progressively Elliptical Commands in Smart Homes 提出PEC-Home以解决智能家居中的逐步省略命令理解问题 large language model
9 BCL: Bayesian In-Context Learning Framework for Information Extraction 提出BCL框架以优化信息提取中的上下文学习 large language model
10 Steerable Cultural Preference Optimization of Reward Models 提出可调文化偏好优化的奖励模型以解决多元文化对齐问题 large language model ✅
11 ScholarSum: Student-Teacher Abstractive Summarization via Knowledge Graph Reasoning and Reflective Refinement 提出ScholarSum以解决科学文献摘要中的流畅性与事实一致性问题 large language model ✅
12 LLMs Struggle to Measure What Distinguishes Students of Different Proficiency Levels: A Study of Item Discrimination in Reading Comprehension Assessment 评估LLMs在阅读理解评估中区分学生能力的能力 large language model
13 RegMix-D: Dynamic Data Mixing via Proxy Training Trajectories 提出RegMix-D以实现动态数据混合提升语言模型预训练效果 large language model
14 The Wrong Kind of Right: Quantifying and Localizing Misfired Alignment in LLMs 提出VETO基准以量化和定位LLMs的错误对齐问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
15 Beyond Reward Engineering: A Data Recipe for Long-Context Reinforcement Learning 提出数据驱动方法以提升长上下文强化学习能力 reinforcement learning large language model
16 DreamReasoner-8B: Block-Size Curriculum Learning for Diffusion Reasoning Models 提出DreamReasoner-8B以解决长链推理中的块大小问题 curriculum learning chain-of-thought ✅
17 Efficient Financial Language Understanding via Distillation with Synthetic Data 提出基于蒸馏与合成数据的高效金融语言理解框架 distillation instruction following
18 PragReST: Self-Reinforcing Counterfactual Reasoning for Pragmatic Language Understanding 提出PragReST以解决大型语言模型的实用推理问题 reinforcement learning distillation large language model
19 Learning User Simulators with Turing Rewards 提出Turing-RL以解决用户模拟器训练问题 reinforcement learning large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页